© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 135619
    Prev
    Next
    INDEX
    Explanations

    again, again, again

    np_acts-logits-general · gemini-2.5-flash-lite

    reunions, again, love, catastrophe

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     adolescentes
    0.45
    ebut
    0.44
     liten
    0.44
     hablando
    0.43
     nuestra
    0.41
     cao
    0.41
     pes
    0.41
     t
    0.40
     natureza
    0.40
     hav
    0.40
    POSITIVE LOGITS
    再び
    0.51
    情报
    0.49
     ponownie
    0.48
    ⚭
    0.48
     ഒഴിവാ
    0.46
     again
    0.45
    Again
    0.45
     reunions
    0.45
     temptation
    0.44
    secrets
    0.44
    Activations Density 0.001%

    No Known Activations